Feat: Enable CUDA support

Dockerfile

@@ -1,7 +1,8 @@
-FROM ubuntu:22.04
+FROM nvidia/cuda:11.8.0-devel-ubuntu22.04
 
 ENV DEBIAN_FRONTEND=noninteractive
 
+# Install base dependencies
 RUN apt-get update && \
     apt-get install -y software-properties-common && \
     add-apt-repository ppa:deadsnakes/ppa && \
@@ -29,50 +30,53 @@ RUN apt-get update && \
 
 RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1
 
-# Set up a new user named "user" with user ID 1000
+# Set up a non-root user
 RUN useradd -m -u 1000 user
 
-# Set home to the user's home directory
+# Set home directory and update PATH
 ENV HOME=/home/user \
 	PATH=/home/user/.local/bin:$PATH
 
 # Set the working directory
 WORKDIR $HOME/app
 
-# Copy requirements first
+# Copy requirements first (as user)
 COPY --chown=user requirements.txt .
 
-# Install dependencies as root
+# Install Python dependencies (as root to manage venv properly)
+# Note: Ensure PyTorch installed picks up CUDA from the base image
 RUN python3 -m venv /opt/mineru_venv && \
     . /opt/mineru_venv/bin/activate && \
     pip install --upgrade pip && \
     pip install -r requirements.txt
 
-# Download model script and set permissions as root
+# Download model script and config template, set permissions (as root)
 RUN wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O $HOME/app/download_models.py && \
     chmod +x $HOME/app/download_models.py && \
     wget https://github.com/opendatalab/MinerU/raw/master/magic-pdf.template.json -O $HOME/app/magic-pdf.json && \
     chown user:user $HOME/app/download_models.py $HOME/app/magic-pdf.json
 
-# Create output directory and set ownership BEFORE switching user for COPY
+# Create output directory and set ownership (as root)
 RUN mkdir -p $HOME/app/output/images && \
     chown -R user:user $HOME/app/output
 
-# Switch to user to run download script and copy app code
+# Switch to non-root user
 USER user
 
-# Run download script
+# Run model download script and configure magic-pdf for CUDA
 RUN . /opt/mineru_venv/bin/activate && \
     python3 $HOME/app/download_models.py && \
     cp $HOME/app/magic-pdf.json $HOME/magic-pdf.json && \
-    sed -i 's|"device": "cpu"|"device": "cpu"|g' $HOME/magic-pdf.json
+    sed -i 's|"device": "cpu"|"device": "cuda"|g' $HOME/magic-pdf.json
 
 # Copy the rest of the application code as the user
-# This will copy into the WORKDIR ($HOME/app)
 COPY --chown=user . .
 
-# Ensure the output dir still has correct permissions after final copy
-# (This might be redundant but can help in some cases)
+# Ensure the output dir still has correct permissions
 RUN chmod -R 755 $HOME/app/output
 
+# Expose the port (optional but good practice)
+EXPOSE 7860
+
+# Run the application
 CMD ["/opt/mineru_venv/bin/uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]